release-rollback

release-rollback is a skill for Claude Code from Prismer-AI/PrismerCloud. It costs 96 tokens per session (4,118 once invoked), scanned A, original, MIT.

A release rollback workflow for the test environment. It changes the release record back to the previous known-good version and can move the Git mirror's release pointer back to that version.

In plain words
What is it for?
Use it to plan and perform a test release rollback, optionally including the bare Git mirror, after a failed post-deployment check.
Why use it?
It provides a controlled way to recover when checks after deployment find a regression. Approval is required, and it stops if there is no earlier good version.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to plan and perform a test release rollback, optionally including the bare Git mirror, after a failed post-deployment check.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/prismer-ai/prismercloud/release-rollback
About the project

Prismer Cloud is an infrastructure layer for AI agents that provides shared learning, compressed context, persistent memory, collaboration, messaging, tasks, identity, and workspaces. It is for agents and the people building or using long-running agent systems that need information and outcomes to persist across sessions. The catalogue entries provide skills, hooks, agents, instructions, and a plugin for using Prismer Cloud.

Prismer-AI/PrismerCloud · 1,386 stars · on GitHub · prismer.cloud

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Prismer-AI/PrismerCloud --skill release-rollback
Clone the repo
git clone --depth 1 https://github.com/Prismer-AI/PrismerCloud

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for release-rollback

README.md
[![agentmods](https://agentmods.dev/badge/skills/prismer-ai/prismercloud/release-rollback/github.svg)](https://agentmods.dev/skills/prismer-ai/prismercloud/release-rollback)
Your own site
<a href="https://agentmods.dev/skills/prismer-ai/prismercloud/release-rollback"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/release-rollback/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for release-rollback

Your own site · 80×15
<a href="https://agentmods.dev/skills/prismer-ai/prismercloud/release-rollback"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/release-rollback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,118 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.04118
Opus 5.5 $0.00038 $0.01647
Sonnet 5.5 $0.00019 $0.00824
Haiku 4.5 $0.00010 $0.00412

Measured 17d ago against content hash 6a8a2966dfa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-rollback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

sdk/apc/skills/release-rollback/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

release-rollback

上线后回归红时的真回滚(apc/01 §2 release-rollback,收口步 10)。它落两个真副作用:

  1. release 账本回退:把当前 current 版本翻 pulled、上一好版本翻回 current(真写 JSON ledger,可读回核验)。
  2. 版本指针回退(给了 --mirror):把 bare mirror 的 refs/heads/release-current 重指到上一好 tag 的 commit(真 git 副作用,git ls-remote 可核验)。

什么时候用:release-verify(部署后回归)红了,需要把 fleet 退回上一个好版本。回滚后应建 bug task 回 bugfix 入口。

承重纪律(发版 skill 的命根子,先记死)

  • 审批门不可跳。未审批 = staged(出回滚计划 dry-run,不执行)。本机替身以 --approved <token> 非空为门(真 approvalId 服务端校验 = M5)。审批人看到的是回滚计划(from→to 版本 + 影响面),不是"agent 说要回滚了"。
  • 无上一好版本 → blocked,绝不空转返绿。账本只有一条、或更早的都已 pulled ⇒ 无从回滚 ⇒ blocked(exit 1)。这是本 verb 的负控注入点:一个"回滚"skill 若在没东西可回滚时也返绿,就是开卷考试。
  • prod 不做。本 skill 是 test 环境的回滚;prod 回滚走人 + M5 路径。

Anti-pattern(直接判红)

  • ❌ 无上一好版本时硬造一个"回滚成功"。planRollback ok:false 就是 blocked,别放松。
  • ❌ 拿到 staged(计划)就以为已回滚。staged 是"等审批",账本还没改。
  • ❌ 手工改 ledger JSON / git update-ref 绕过 verb 的审批门和 plan 计算。

工具契约(签名以此为准)

apc 不在 PATH——在仓库根用 npx tsx sdk/apc/bin/apc.ts <sub>。

命令 作用 退出码
npx tsx sdk/apc/bin/apc.ts release rollback [--ledger <path>] [--mirror <bare>] [--approved <token>] [--json] 算回滚计划 → 审批门 → 写账本回退(+ 可选 mirror ref 重指) 0 green(applied)· 3 staged(计划待审批)· 1 blocked(无上一好版本)

--json 字段(名以此为准):

  • 顶层:{ verb:'rollback', decision, ledgerPath, plan, approved, applied, mirrorRepointed, blockers:[], notes:[] }
  • plan:{ ok:true, from:{version,tag,status}, to:{version,tag,status}, next:[...] } 或 { ok:false, reason }
  • ledger 条目形状:{ version, tag, status:'current'|'pulled'|'superseded', ts }(current 唯一)

Workflow

1. 备好 release 账本(本机替身)

账本记录发过的版本序列,当前版本 status:'current'。本机替身用一份 JSON(真 release-status 行的替身):

cat > /tmp/apc-rollback-ledger.json <<'JSON'
[
  { "version": "2.0.5", "tag": "k8s-test-20260720-v2.0.5", "status": "superseded", "ts": "2026-07-20T00:00:00Z" },
  { "version": "2.0.6", "tag": "k8s-test-20260722-v2.0.6", "status": "superseded", "ts": "2026-07-22T00:00:00Z" },
  { "version": "2.0.7", "tag": "k8s-test-20260724-v2.0.7", "status": "current",    "ts": "2026-07-24T00:00:00Z" }
]
JSON

Read the full file on GitHub · 215 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 17d ago First seen · 215 lines · 96 tokens per session scan A 6a8a2966dfa0

Subscribe to this mod's changes

release-rollback is a skill published in the GitHub repository Prismer-AI/PrismerCloud (1,386 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 4,118 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.